Skip to content

feat: complete repo explainer agent with eval harness and optimizer#1

Merged
AxaySharma merged 16 commits into
mainfrom
dev
Jun 13, 2026
Merged

feat: complete repo explainer agent with eval harness and optimizer#1
AxaySharma merged 16 commits into
mainfrom
dev

Conversation

@AxaySharma

Copy link
Copy Markdown
Owner

What this PR delivers

A complete agentic AI system built on the Claude Agent SDK that reads
any codebase and answers natural language questions about it.

Three pillars

🤖 Agent — Multi-step agentic loop with 5 filesystem tools. Reads
files, searches code, maps dependencies, synthesizes grounded answers.
Supports both local paths and GitHub URLs transparently.

📊 Eval Harness — 8 test cases with 4 weighted metrics (topic
coverage, hallucination penalty, answer length, groundedness).
Saves full JSON reports per run.

Optimizer — Automated prompt tuning loop. Runs evals, identifies
failures, asks Claude to improve the system prompt, keeps improvements
and reverts regressions.

Results

Run Pass Rate Avg Score Groundedness
Baseline 100% 0.9917 1.0000

Infrastructure

  • 25 unit tests — all passing
  • GitHub Actions CI on every push
  • Clean commit history on dev

@AxaySharma
AxaySharma merged commit 57bf80e into main Jun 13, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant